CVE-2025-48943

vLLM allows clients to crash the openai server with invalid regex

MEDIUM
6.5
CVSS Score
Published: May 30, 2025 at 06:36 PM UTC
Updated: June 17, 2026 at 09:30 AM UTC
1 product affected across 1 vendorvLLM

Using vllm by vllm-project?

Get instant alerts when new vulnerabilities affect vllm - before attackers find them.

Real-time alertsTrack your software stackFree plan available
Severity
MEDIUM6.5
Exploit prediction
EPSS 0.5%
SSVC
No known exploit

Description

vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

Affected

Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.

v < 0.9.00.8.0 ≤ v < 0.9.0
Affected range stops below 0.9.0, so it looks safe — our inference, not a vendor statement

SSVC — Action Prioritization

SSVCNo known exploitNot automatablePartial impact

SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.

CVSS

6.5MEDIUMGitHub_M
Attack Vector
NETWORK
Complexity
LOW
Privileges
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH
Vector?

Quick Info

StatusANALYZED
CWE
CWE-248

Get alerted

Stop reading CVE feeds looking for your own stack

Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.

Free plan, no card